A Photovoltaic Output Backcast and Forecast Method based on Cloud Cover and Historical Data

Damilola Owoeye, Maxim Shcherbakov, and Valeriy Kamaev


photovoltaic output forecast, backcast technique, clustering, k-means


Owing to the fact that input data for existing PV forecast algorithms are hard to come by, there is the need to develop a method based on data that is relatively easy to obtain and one with a much simpler algorithm which still produces acceptable results. This paper proposes a method for photovoltaic output backcast and forecast using cloud cover and historical data. The method is about five times more efficient than the benchmark model.

Important Links:

Go Back